Wayne (Wen-Yan) Wu
Associate Director of R&D @ XR-Lab & SmartVideo Group, SenseTime Group Inc.
Research Scientist @ XR-Research Group, Shanghai AI Lab.

Hey, thanks for stopping by! 😄
I am currently an Associate Director of R&D at SenseTime Group Inc., working with Chen Qian and Xiaogang Wang, where I lead the product, research and development of XR-Lab and SmartVideo Group with 50+ members. Also, I am a Research Scientist at Shanghai AI Lab, where I lead the group of XR-Research.
Previously, I obtained my PhD in the BNRist Center, Department of Computer Science and Technology at Tsinghua University, under the supervision of Qiang Zhou and Yici Cai. During my PhD, I spent wonderful times as a visiting PhD student at MMLab@NTU in 2019, advised by Chen Change Loy. Prior to that, I had the pleasure to join SenseTime Research as a full-time intern in 2016.
My research interests lie at the intersection of Computer Vision, Computer Graphics and XR, with focus on generative model, neural rendering and digital human.
News
May, 2022 | 2 papers got accepted by SIGGRAPH 2022. |
---|---|
Mar, 2022 | 3 papers got accepted by CVPR 2022. |
Jul, 2021 | 6 papers got accepted by CVPR/ICCV/NeurIPS in 2021. |
Aug, 2020 | We are organizing DeeperForensics Challenge on Real-World Face Forgery Detection, ECCV 2020. |
Aug, 2020 | We are organizing Workshop on Sensing, Understanding and Synthesizing Humans, ECCV 2020. |
Jul, 2020 | 5 papers got accepted by CVPR/ECCV/NeurIPS in 2020. |
Jul, 2020 | We released MMAction2, OpenMMLab’s Next Generation Action Understanding Toolbox. |
Jul, 2020 | We released MMEditing, OpenMMLab’s Image and Video Editing Toolbox. |
Oct, 2019 | We are organizing Workshop on Statistical Deep Learning for Computer Vision, ICCV 2019. |
Jul, 2018 | 5 papers got accepted by CVPR/ICCV/ICLR in 2019. |
Selected Publications
- StyleGAN-Human: A Data-Centric Odyssey of Human GenerationTechnical report, arXiv:2205.15996, 2022
- Generalizable Neural Performer: Learning Robust Radiance Fields for Human Novel View SynthesisTechnical report, arXiv:2204.11798, 2022
- Text2Human: Text-Driven Controllable Human Image GenerationACM Transaction on Graphics (SIGGRAPH), 2022
- TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial EditingConference on Computer Vision and Pattern Recognition (CVPR), 2022
- Focal Frequency Loss for Image Reconstruction and SynthesisInternational Conference on Computer Vision (ICCV), 2021
- Everything’s Talkin’: Pareidolia Face ReenactmentConference on Computer Vision and Pattern Recognition (CVPR), 2021
- MEAD: A Large-Scale Audio-Visual Dataset for Emotional Talking-Face GenerationEuropean Conference on Computer Vision (ECCV), 2020
- DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery DetectionConference on Computer Vision and Pattern Recognition (CVPR), 2020
- TransMoMo: Invariance-Driven Unsupervised Video Motion RetargetingConference on Computer Vision and Pattern Recognition (CVPR), 2020
- TransGaGa: Geometry-Aware Unsupervised Image-to-Image TranslationConference on Computer Vision and Pattern Recognition (CVPR), 2019
- ReenactGAN: Learning to Reenact Faces via Boundary TransferEuropean Conference on Computer Vision (ECCV), 2018
- Look at Boundary: A Boundary-Aware Face Alignment AlgorithmConference on Computer Vision and Pattern Recognition (CVPR), 2018